{"id":15114,"name":"bpeasy","description":"Fast bare-bones BPE for modern tokenizer training","url":"https://github.com/gautierdag/bpeasy","last_synced_at":"2025-09-04T22:40:23.507Z","repository":{"id":212655379,"uuid":"716786243","full_name":"gautierdag/bpeasy","owner":"gautierdag","description":"Fast bare-bones BPE for modern tokenizer training","archived":false,"fork":false,"pushed_at":"2025-06-23T15:09:38.000Z","size":1482,"stargazers_count":164,"open_issues_count":0,"forks_count":5,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-08-31T13:48:12.689Z","etag":null,"topics":["bpe","tokenization","tokenizer"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/gautierdag.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2023-11-09T21:47:01.000Z","updated_at":"2025-08-06T21:14:16.000Z","dependencies_parsed_at":"2025-04-12T04:28:40.725Z","dependency_job_id":null,"html_url":"https://github.com/gautierdag/bpeasy","commit_stats":null,"previous_names":["gautierdag/bpeasy"],"tags_count":7,"template":false,"template_full_name":null,"purl":"pkg:github/gautierdag/bpeasy","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gautierdag","download_url":"https://codeload.github.com/gautierdag/bpeasy/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273685277,"owners_count":25149719,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-04T02:00:08.968Z","response_time":61,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"owner":null,"packages":[{"id":8646089,"name":"bpeasy","ecosystem":"pypi","description":"Fast bare-bones BPE for modern tokenizer training","homepage":null,"licenses":"MIT","normalized_licenses":["MIT"],"repository_url":"https://github.com/gautierdag/bpeasy","keywords_array":["tokenizer","tokenization","bpe"],"namespace":null,"versions_count":7,"first_release_published_at":"2023-12-15T12:46:51.000Z","latest_release_published_at":"2025-06-23T15:18:19.000Z","latest_release_number":"0.1.6","last_synced_at":"2025-08-31T13:36:37.449Z","created_at":"2023-12-15T13:03:08.664Z","updated_at":"2025-08-31T13:48:33.937Z","registry_url":"https://pypi.org/project/bpeasy/","install_command":"pip install bpeasy --index-url https://pypi.org/simple","documentation_url":"https://bpeasy.readthedocs.io/","metadata":{"funding":null,"documentation":null,"classifiers":["License :: OSI Approved :: MIT License","Programming Language :: Python :: 3.10","Programming Language :: Python :: 3.11","Programming Language :: Python :: 3.12","Programming Language :: Python :: 3.13","Programming Language :: Python :: 3.8","Programming Language :: Python :: 3.9","Programming Language :: Python :: Implementation :: CPython","Programming Language :: Python :: Implementation :: PyPy","Programming Language :: Rust"],"normalized_name":"bpeasy","project_status":null},"repo_metadata":{"id":212655379,"uuid":"716786243","full_name":"gautierdag/bpeasy","owner":"gautierdag","description":"Fast bare-bones BPE for modern tokenizer training","archived":false,"fork":false,"pushed_at":"2025-06-23T15:09:38.000Z","size":1482,"stargazers_count":160,"open_issues_count":0,"forks_count":5,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-07-28T16:54:40.534Z","etag":null,"topics":["bpe","tokenization","tokenizer"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/gautierdag.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2023-11-09T21:47:01.000Z","updated_at":"2025-07-26T08:54:41.000Z","dependencies_parsed_at":"2025-04-12T04:28:40.725Z","dependency_job_id":null,"html_url":"https://github.com/gautierdag/bpeasy","commit_stats":null,"previous_names":["gautierdag/bpeasy"],"tags_count":7,"template":false,"template_full_name":null,"purl":"pkg:github/gautierdag/bpeasy","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gautierdag","download_url":"https://codeload.github.com/gautierdag/bpeasy/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":272988781,"owners_count":25026959,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-08-31T02:00:09.071Z","response_time":79,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"},"tags":[{"name":"v0.1.5","sha":"775e311c1d9e606d4bd4ad22d38487b90dc532f7","kind":"commit","published_at":"2025-04-02T09:24:29.000Z","download_url":"https://codeload.github.com/gautierdag/bpeasy/tar.gz/v0.1.5","html_url":"https://github.com/gautierdag/bpeasy/releases/tag/v0.1.5","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/gautierdag/bpeasy@v0.1.5","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/tags/v0.1.5","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/tags/v0.1.5/manifests"},{"name":"v0.1.4","sha":"7a6b0cc0ba0b3a1b148269770ff7ce26ce4ed472","kind":"commit","published_at":"2024-08-29T16:51:48.000Z","download_url":"https://codeload.github.com/gautierdag/bpeasy/tar.gz/v0.1.4","html_url":"https://github.com/gautierdag/bpeasy/releases/tag/v0.1.4","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/gautierdag/bpeasy@v0.1.4","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/tags/v0.1.4","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/tags/v0.1.4/manifests"},{"name":"v0.1.3","sha":"a9d7a5b5b6c6fdaa40dddd763b381799a3b1f338","kind":"commit","published_at":"2024-08-23T10:33:21.000Z","download_url":"https://codeload.github.com/gautierdag/bpeasy/tar.gz/v0.1.3","html_url":"https://github.com/gautierdag/bpeasy/releases/tag/v0.1.3","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/gautierdag/bpeasy@v0.1.3","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/tags/v0.1.3","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/tags/v0.1.3/manifests"},{"name":"v0.1.2","sha":"3b232e90d33de960be258cd6ce7107ef8d89676c","kind":"commit","published_at":"2023-12-19T10:44:17.000Z","download_url":"https://codeload.github.com/gautierdag/bpeasy/tar.gz/v0.1.2","html_url":"https://github.com/gautierdag/bpeasy/releases/tag/v0.1.2","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/gautierdag/bpeasy@v0.1.2","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/tags/v0.1.2","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/tags/v0.1.2/manifests"},{"name":"v0.1.1","sha":"6ade31675212f412810d1b305f31d48556b76a8d","kind":"commit","published_at":"2023-12-15T14:47:35.000Z","download_url":"https://codeload.github.com/gautierdag/bpeasy/tar.gz/v0.1.1","html_url":"https://github.com/gautierdag/bpeasy/releases/tag/v0.1.1","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/gautierdag/bpeasy@v0.1.1","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/tags/v0.1.1","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/tags/v0.1.1/manifests"},{"name":"v0.0.2","sha":"468698254b79e1a72d86775e1ca926762870a540","kind":"commit","published_at":"2023-12-15T14:33:01.000Z","download_url":"https://codeload.github.com/gautierdag/bpeasy/tar.gz/v0.0.2","html_url":"https://github.com/gautierdag/bpeasy/releases/tag/v0.0.2","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/gautierdag/bpeasy@v0.0.2","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/tags/v0.0.2","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/tags/v0.0.2/manifests"},{"name":"v0.0.1","sha":"15baad8c817a69c21d833abccc9f933585126be6","kind":"commit","published_at":"2023-12-15T12:24:30.000Z","download_url":"https://codeload.github.com/gautierdag/bpeasy/tar.gz/v0.0.1","html_url":"https://github.com/gautierdag/bpeasy/releases/tag/v0.0.1","dependencies_parsed_at":null,"dependency_job_id":null,"purl":"pkg:github/gautierdag/bpeasy@v0.0.1","tag_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/tags/v0.0.1","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/tags/v0.0.1/manifests"}]},"repo_metadata_updated_at":"2025-08-31T13:48:33.937Z","dependent_packages_count":0,"downloads":1536,"downloads_period":"last-month","dependent_repos_count":0,"rankings":{"downloads":null,"dependent_repos_count":66.97090019862763,"dependent_packages_count":10.150542857468132,"stargazers_count":null,"forks_count":null,"docker_downloads_count":null,"average":38.56072152804788},"purl":"pkg:pypi/bpeasy","advisories":[],"docker_usage_url":"https://docker.ecosyste.ms/usage/pypi/bpeasy","docker_dependents_count":null,"docker_downloads_count":null,"usage_url":"https://repos.ecosyste.ms/usage/pypi/bpeasy","dependent_repositories_url":"https://repos.ecosyste.ms/api/v1/usage/pypi/bpeasy/dependencies","status":null,"funding_links":[],"critical":null,"issue_metadata":{"last_synced_at":"2025-07-28T16:54:40.750Z","issues_count":5,"pull_requests_count":0,"avg_time_to_close_issue":799975.5,"avg_time_to_close_pull_request":null,"issues_closed_count":4,"pull_requests_closed_count":0,"pull_request_authors_count":0,"issue_authors_count":5,"avg_comments_per_issue":3.0,"avg_comments_per_pull_request":null,"merged_pull_requests_count":0,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":5,"past_year_pull_requests_count":0,"past_year_avg_time_to_close_issue":799975.5,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":4,"past_year_pull_requests_closed_count":0,"past_year_pull_request_authors_count":0,"past_year_issue_authors_count":5,"past_year_avg_comments_per_issue":3.0,"past_year_avg_comments_per_pull_request":null,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":0,"issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/issues","maintainers":[],"active_maintainers":[]},"versions_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/bpeasy/versions","version_numbers_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/bpeasy/version_numbers","dependent_packages_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/bpeasy/dependent_packages","related_packages_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages/bpeasy/related_packages","maintainers":[{"uuid":"gautierdag","login":"gautierdag","name":null,"email":null,"url":null,"packages_count":5,"html_url":"https://pypi.org/user/gautierdag/","role":null,"created_at":"2023-12-15T13:06:39.053Z","updated_at":"2023-12-15T13:06:39.053Z","packages_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/maintainers/gautierdag/packages"}],"registry":{"name":"pypi.org","url":"https://pypi.org","ecosystem":"pypi","default":true,"packages_count":724922,"maintainers_count":308248,"namespaces_count":0,"keywords_count":237984,"github":"pypi","metadata":{"funded_packages_count":50481},"icon_url":"https://github.com/pypi.png","created_at":"2022-04-04T15:19:23.364Z","updated_at":"2025-09-04T05:23:51.177Z","packages_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/packages","maintainers_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/maintainers","namespaces_url":"https://packages.ecosyste.ms/api/v1/registries/pypi.org/namespaces"}}],"commits":{"id":9408476,"full_name":"gautierdag/bpeasy","default_branch":"main","committers":[{"name":"Gautier Dagan","email":"s2234411@ed.ac.uk","login":"gautierdag","count":53}],"total_commits":53,"total_committers":1,"total_bot_commits":0,"total_bot_committers":0,"mean_commits":53.0,"dds":0.0,"past_year_committers":[{"name":"Gautier Dagan","email":"s2234411@ed.ac.uk","login":"gautierdag","count":11}],"past_year_total_commits":11,"past_year_total_committers":1,"past_year_total_bot_commits":0,"past_year_total_bot_committers":0,"past_year_mean_commits":11.0,"past_year_dds":0.0,"last_synced_at":"2025-05-18T07:53:44.429Z","last_synced_commit":"775e311c1d9e606d4bd4ad22d38487b90dc532f7","created_at":"2025-03-30T11:31:42.712Z","updated_at":"2025-05-18T07:53:44.430Z","commits_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/commits","host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-04T00:00:25.936Z","repositories_count":5480019,"commits_count":853389012,"contributors_count":31098138,"owners_count":906558,"icon_url":"https://github.com/github.png","host_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://commits.ecosyste.ms/api/v1/hosts/GitHub/repositories"}},"issues_stats":{"full_name":"gautierdag/bpeasy","html_url":"https://github.com/gautierdag/bpeasy","last_synced_at":"2025-08-31T13:48:33.648Z","status":"error","issues_count":5,"pull_requests_count":0,"avg_time_to_close_issue":799975.5,"avg_time_to_close_pull_request":null,"issues_closed_count":4,"pull_requests_closed_count":0,"pull_request_authors_count":0,"issue_authors_count":5,"avg_comments_per_issue":3.0,"avg_comments_per_pull_request":null,"merged_pull_requests_count":0,"bot_issues_count":0,"bot_pull_requests_count":0,"past_year_issues_count":5,"past_year_pull_requests_count":0,"past_year_avg_time_to_close_issue":799975.5,"past_year_avg_time_to_close_pull_request":null,"past_year_issues_closed_count":4,"past_year_pull_requests_closed_count":0,"past_year_pull_request_authors_count":0,"past_year_issue_authors_count":5,"past_year_avg_comments_per_issue":3.0,"past_year_avg_comments_per_pull_request":null,"past_year_bot_issues_count":0,"past_year_bot_pull_requests_count":0,"past_year_merged_pull_requests_count":0,"created_at":"2025-03-30T11:31:42.838Z","updated_at":"2025-09-02T10:20:30.403Z","repository_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy","issues_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories/gautierdag%2Fbpeasy/issues","issue_labels_count":{"enhancement":1,"question":1},"pull_request_labels_count":{},"issue_author_associations_count":{"NONE":5},"pull_request_author_associations_count":{},"issue_authors":{"JonasGeiping":1,"filemon11":1,"umarbutler":1,"bauwenst":1,"depshad":1},"pull_request_authors":{},"host":{"name":"GitHub","url":"https://github.com","kind":"github","last_synced_at":"2025-09-04T00:00:25.939Z","repositories_count":10082445,"issues_count":31251663,"pull_requests_count":96134747,"authors_count":10694148,"icon_url":"https://github.com/github.png","host_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/repositories","owners_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/owners","authors_url":"https://issues.ecosyste.ms/api/v1/hosts/GitHub/authors"},"past_year_issue_labels_count":{"enhancement":1},"past_year_pull_request_labels_count":{},"past_year_issue_author_associations_count":{"NONE":3},"past_year_pull_request_author_associations_count":{},"past_year_issue_authors":{"bauwenst":1,"filemon11":1,"umarbutler":1},"past_year_pull_request_authors":{},"maintainers":[],"active_maintainers":[]},"events":{"total":{"CreateEvent":1,"ReleaseEvent":1,"IssuesEvent":3,"WatchEvent":24,"IssueCommentEvent":1,"PushEvent":3,"ForkEvent":4},"last_year":{"CreateEvent":1,"ReleaseEvent":1,"IssuesEvent":3,"WatchEvent":24,"IssueCommentEvent":1,"PushEvent":3,"ForkEvent":4}},"keywords":["bpe","tokenization","tokenizer"],"dependencies":null,"score":12.437454171362795,"created_at":"2025-09-04T15:50:46.037Z","updated_at":"2025-10-07T08:08:19.306Z","avatar_url":"https://github.com/gautierdag.png","language":"Python","category":null,"sub_category":null,"monthly_downloads":1536,"funding_links":[],"readme_doi_urls":[],"works":{},"citation_counts":{},"total_citations":0,"keywords_from_contributors":[],"project_url":"https://science.ecosyste.ms/api/v1/projects/15114","html_url":"https://science.ecosyste.ms/projects/15114","bibtex_url":"https://science.ecosyste.ms/projects/15114/export.bibtex","apalike_url":"https://science.ecosyste.ms/projects/15114/export.apalike"}